WIAMIS 2013, 14th International Workshop on Image and Audio Analysis for Multimedia Interactive Services, 3-5 July, Paris, France
This paper presents a method for predicting the parts of a video that could be marked as "interesting" by a user. Our approach consists in considering the three competing criteria
: salience, expressivity and significativity and to automatically combine the three corresponding functions of interest. We evaluates this system on a user-annotated test set. Results demonstrate that, in spite of the intrinsic subjectivity of user choices, the system succeeds in finding about 51% of interesting segments.
Type:
Conference
City:
Paris
Date:
2013-07-03
Department:
Data Science
Eurecom Ref:
4037
Copyright:
© 2013 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
See also:
